Coding agents & developer tools
Testing & QA agents
988 agents · most starred first
Testing & QA agents, page 4 of 10
AI-First SAP UI5 Test Automation for Playwright
UXCascade: Scalable Usability Testing with Simulated User Agents
Your AI Quality Agent, putting app testing on autopilot.
Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.
Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done.
Agent-neutral AI testing skills for Katalon True Platform: 18 skills covering the full testing lifecycle, operated through the Katalon MCP. Works with Claude Code, Copilot, Codex, Cursor, and any Agent Plugins client.
Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.
AI testing agent for pull requests: maps the blast radius of a diff, runs only the tests that cover it, drafts the ones that are missing, and gates the merge on a score. Plain-English YAML, no selectors. Local-first, BYOK.
An autonomous local-first AI Agent that generates, runs, and self-heals Python unit tests in real-time. Supports Ollama, Groq, and many frameworks such as pytest.
Your coding agent says it works. Gopnik tries to prove it doesn't — against the code, the delivered revision, and the checks themselves.
A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).
WCAG 2.1/2.2 accessibility audit CLI and AI skill with explicit manual-review boundaries.
Runs the base branch's tests against a PR's code and checks the description's claims against what actually ran. Signed evidence from CI.
Agent-first browser testing: deterministic replay, evidence packs, typed verdicts, and portable skills for coding agents.
SWEeper-Bench: Can agents discover bugs in interactive software? 200 real bugs in 200 open-source web apps; agents get only the code and an open-ended prompt, and an agentic verifier checks each fix in the browser.
Session Recorder by Proofline. Free, open-source Chrome bug reports with annotations, voice, screenshots and one-click GitHub issues.
GitHub template for agent-testable SaaS apps. Next.js 16 + shadcn/ui + Neon Postgres + agent-browser e2e testing via accessibility tree.
Robot Framework and OpenAI integration
Playwright + TypeScript automation framework for UI and API testing with page objects, shared fixtures, reusable services, and AI-assistant guidance through AGENTS.md and local skills
The validation loop that stops AI coding agents from claiming work is done before it actually is.
AI-driven Android UI test automation — plain-language cases run by an agent on real devices over any network (no ADB/scripts), with visual reports & self-learning.
Stop trusting 'done'. Make AI coding agents prove their work — frozen specs, tamper-detected tests, an independent blind verifier, hard-blocking gates. Fails loudly instead of pretending. For Claude Code, Codex, OpenCode & any Agent Skills runtime. No unverified work passes.
Autonomous AI agent swarm for visual, functional, and accessibility testing of Android apps and mobile web - powered by vision-capable AI models and containerized Android instances.
Verified tutorials and demo videos from your README. An AI agent runs it in a hardened Docker sandbox and replays it in a fresh container before anything is published.
Turn requirements into Playwright plans, tests, runs, and repair workflows with a self-hosted AI agent.
AI-powered regression testing platform using AST analysis, hybrid RAG, LangGraph agents, sandboxed test execution, and automated failure diagnosis.
Tested accessibility skills, CLI, MCP server, and GitHub Action for agent-assisted audits and regression checks.
Your coding agent says it's done. provepr makes it prove it: runs the PR's claims in a real browser and feeds the evidence back to Claude Code / Codex.
15 named silent-failure modes - validation that passes while nothing is being checked. Each with a runnable reproduction, a fixing recipe and a negative control, plus a self-testing linter.
Automatically repair broken Playwright E2E tests. When a UI change renames or restructures an element and a test's selector breaks, the engine diagnoses the failure, patches the broken selector/wait, verifies the new selector against the live DOM, then re-runs the test until it passes (or a retry cap is hit) and writes the fix back
Working files for the Vibe Testing course — logs to investigate, an epic to refine, an ng-apimock server, and a Postman collection. For use with QAcart-Premium/ship-app.
A lightweight API testing CLI-based framework designed for automation-friendly, scriptable API testing
Self-Reinforced Testing Framework (SRTF) for AI Agents.
A collection of skills focused on end-to-end automation for AI agents.
pytest plugin for deterministic testing of AI agents. Assert agent actions, not vibes.
Automated TikTok-style video review of every PR.
From breakpoints to test cases — AI-powered test generation straight from your debugger.
QA Maestro is an intelligent QA automation system that uses multiple AI agents orchestrated through MAF to perform end-to-end testing workflows.
A robust agentic workflow for LLM-based development. Features role-based orchestration (Analyst, Architect, Developer), strict Stub-First methodology, and automated TDD/VDD cycles.
CI for Claude Skills — lint, eval, and regression-test SKILL.md files across a model matrix, with a self-growing eval loop that turns uncovered regressions into permanent test cases.
A verification layer for AI coding agents. 250+ real-protocol service emulators (Stripe, Postgres, Slack, S3, OpenAI…) on local Docker.
An AI agent that drives a real browser, audits any web app against UX/functional/conversion rubrics, and shows evidence-backed findings. Works with any OpenAI-compatible LLM.
Let vision-capable AI act as demanding customers and catch product problems before launch.
context-aware API testing toolkit for Nodejs right in your terminal.
GenPark AI Agent Skill - Zeller's Delta Debugging (ddmin) algorithm minimizing failing code snippets, complex payloads, and config files to minimal reproducible examples (MRE).
GenPark AI Agent Skill - Automated program repair (APR) engine mutating Python ASTs, applying template-driven bug fixes, and validating candidate patches.
GenPark AI Agent Skill - Dynamically synthesizes and evaluates runtime assertions, pre/post-conditions, and state invariants to detect data corruption before crashes occur.
GenPark AI Agent Skill - Synthesizes property-based and counterfactual unit test inputs (fuzzing boundary values, null states, edge cases) to reproduce runtime tool bugs.
GenPark AI Agent Skill - Parses Python stack traces into structured traceback frames, calculates Tarantula/Ochiai line suspiciousness scores, and isolates root-cause bug locations.
GenPark AI Agent Skill - Concolic testing and symbolic branch inversion engine recording concrete-symbolic execution paths and targeting unvisited code branches.
GenPark AI Agent Skill - Dijkstra's Weakest Precondition (wp) predicate transformer calculus engine backward-propagating postconditions through assignment statements and branch conditions.
GenPark AI Agent Skill - Presburger linear integer arithmetic decision procedure solving systems of linear inequalities for agent safety guard synthesis.
GenPark AI Agent Skill - Loop invariant inductiveness and total correctness prover verifying initialization, preservation, and postcondition implication.
GenPark AI Agent Skill - Deductive program verifier validating Hoare logic triplets {P} C {Q} across state transitions, assignment axioms, and conditional branches.
Self-healing locators for Playwright. When a selector breaks, an AI model finds the element you meant, verifies it and caches the fix. Works with OpenAI, Claude, Gemini or a local Ollama model.
QA via natural language
E2E testing for chatbots
A Tool that Allows You Run PyTest within Jupyter Notebook Cells
An autonomous AI-powered QA testing tool designed to drastically reduce the cost and time of E2E test maintenance.
Own your agent harness: an inspectable Python loop, run evidence, tests and evals, and reusable, reviewable agent packages.
Claude Code skills for automated E2E testing with agent-browser (Playwright CLI). Discover routes, generate YAML test manifests, execute with hybrid LLM assertions, track regressions.
Demo repository for agentic TDD pair programming.
Vision-powered UX simulation engine for Claude Code. Renders pages in a real browser, captures 36+ screenshots across viewports, clicks through interactive elements, maps CTA funnels, tests signup flows, and scores across 7 UX dimensions. Replaces manual user testing with automated multi-viewport analysis.
AI-powered QA Architect agent — generates ISTQB/OWASP/IEEE/ISO-grounded Test Strategies, Risk Registers, Effort Estimates & Test Plans via RAG. Cloud-hosted (Mistral API + Pinecone).
基于 LLM Agent 的智能接口测试平台:RAG 文档问答 / 用例自动生成与评审 / LangGraph 多Agent工作流 / 失败归因分析 / pytest 回归脚本沉淀,支持多模型切换与多被测系统零代码接入
HackerRank Orchestrate hackathon AI agents: a multi-modal damage-claim verifier (3rd of 1,773) and a support-triage RAG agent (60th of 1,349). The model describes; plain code decides
AI Web:面向 Web 自动化测试的自然语言 Browser Agent 执行平台,支持多浏览器调度、任务队列与可追溯报告。
An open-source autonomous QA agent that spawns AI-powered user agents and unleashes them on your product - web, mobile, or desktop. Each agent navigates independently, makes decisions, hits dead ends, finds bugs, and reports back. All without writing a single test script.
An embeddable AI dev agent for your running app — chat, page control, and live tests, injected into the page via a Vite plugin.
GenPark AI Agent Skill - Dynamic mock object synthesizer and behavioral fuzzer generating contract-conforming test doubles for agent tool sandboxing.
Acceptance testing for LLM systems via role subagents (Claude Code plugin)
Claude writes the code. Codex reviews it. You approve twice. A role-per-worktree AI agent TDD pipeline with Gherkin specs, mutation testing, and a manual-test gate.
Web UI visual regression and bounding box displacement analyzer detecting layout shifts
Claimed ≠ verified. evalid is a runtime verification layer for coding agents: it seals each test run and replays it from a clean snapshot, so a claim only ships if the evidence replays green.
Multi-agent TDD/SDD scaffold. Rebuilds Spring Boot apps from specs + tests using parallel headless Claude agents with context isolation.
Local acceptance gate for coding agents: blocks false-green done until task-scoped proof is rechecked.
Audits time-based machine learning backtests, walk-forward validation, rolling retraining, forecasting evaluations, and temporal train/test pipelines for data leakage, faulty split logic, invalid feature timing, target leakage, calibration/tuning leakage, and misleading experiment comparisons.
🏆 Category Winner - Google All Things Agentic Hackathon 2026 ShipGuard - an autonomous agent that turns TestFlight crash reports and beta feedback into Xcode-validated GitHub pull requests. It investigates your codebase, tests minimal fixes on a macOS runner, and leaves the final merge to you.
Automates E2E testing using LLM Vision and Natural Language. Talos reads your design (Figma), drives your app (Web/Mobile), and heals itself when code changes—replacing brittle scripts with autonomous visual verification.
一套 AI 辅助的自动化测试工具链
Anyany.js is a Node.js-based generative AI framework for software testing, supporting both local (Ollama) and cloud (OpenAI) models
An open-source, multi-agent AI framework for Playwright test automation — featuring a 2D pixel-art office, live SSE telemetry, and Gemini / Ollama LLM routing.
This project uses UVM to verify an SPI Slave connected to internal RAM. It includes multiple agents (active and passive) and integrates assertion-based verification for both SPI and RAM behavior.
We can test scenario of chat bots easily :)
👩🔬 Test your Dialogflow/Actions on Google fulfillments like never before
AI-powered GitHub Action that analyzes test quality, provides scores, identifies issues, and suggests improvements through OpenAI's GPT models. Posts detailed reports directly to your pull requests.
Use LLM to convert requirement in plain english to Playwright script
Instantly generate mock REST APIs powered by LLMs (GPT/Gemini). Just describe your endpoint—MockGen does the rest. Docker-ready, fast, and open source.
Sistema de generación automática de tests de Playwright usando Claude AI
Agent Skill for creating and managing TYPO3 extension tests | Claude Code compatible
Autonomous agent monitoring GenAI, AI agents, QA & testing landscape – delivering structured intelligence reports for QA Managers
AI-driven mobile app testing via MCP. Any AI coding agent can test any Android app - no test framework, no boilerplate, no testIDs
Automatically generate BDD test scripts from JIRA stories using AI! This tool leverages OpenAI's language models and LangChain to analyze your JIRA stories and generate comprehensive Gherkin-style acceptance criteria.
Deterministic mobile UI checks for AI coding agents. One Zig binary drives real iOS/Android devices, returns a typed pass/fail, and writes a replayable trace you can gate a merge on. No LLM inside.
AI-native web testing: describe what to test in plain English, and Argus plans, executes, and reports — no scripts required.
Link features, claims, tests, and evidence into verifiable releases stored on Walrus.
Multi-agent LangGraph app turning raw requirements into backlog-ready user stories, ACs, and test cases. Live Gemini-Flash CI eval gate + nightly N=10 adversarial regression.
A Claude Code command that refuses to call anything shipped until a separate fresh-context verifier proves it in the real world.
Make Claude Code and Codex prove their work — runs advance only when your tests, lint, and typecheck actually pass. Open-source Go runtime.
Accessibility Skills (accessibility-skills): AI skills that plan, review, test, and audit web accessibility (WCAG 2.2) — Accessibility Planner, Critic, Tester, Perspective Audit, and Bug Reporting for Claude Code, Codex, and local models, with cross-model benchmarks.